fix(genai) : respect retry_delay from Gemini 429 ResourceExhausted
#946
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lkuligin
approved these changes
May 29, 2025
|
Hey @lkuligin , can you please merge this, thanks. |
|
@SYED-M-HUSSAIN linter is failing |
mdrxy
requested changes
Sep 15, 2025
| """ | ||
|
|
||
|
|
||
| def _create_retry_decorator( |
There was a problem hiding this comment.
Why do we remove the params?
mdrxy
changed the title
retry_delay from Gemini 429 ResourceExhausted
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Description
This PR fixes the retry logic in the LangChain Google integration to respect the
retry_delayfield returned by the Gemini API inResourceExhausted(429) errors. Previously, the retry mechanism ignored the server-suggested delay, causing premature retries and quota issues. The fix introduces a custom wait strategy that uses the server-provided delay when available and falls back to exponential backoff otherwise. This aligns client retry behavior with Gemini’s rate limiting guidance, improving reliability and reducing quota exhaustion errors.Relevant issues
retry_delayis not used to guide retry interval #945 (genai: retry_delay is not used to guide retry interval)Type
🐛 Bug Fix
Changes (optional)
wait_with_server_retry_delaycustom wait strategy class_create_retry_decoratorto use this custom wait handler